© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9418
    Prev
    Next
    INDEX
    Explanations

    the word "dominant", sometimes in conjunction with "primary"

    oai_token-act-pair · gemini-2.0-flash

    dominant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.62
     M
    -0.57
     utafitiHapana
    -0.56
      
    -0.55
    й
    -0.54
     Ber
    -0.54
    acetyl
    -0.53
    lorette
    -0.53
    helin
    -0.53
     dominated
    -0.53
    POSITIVE LOGITS
     myſelf
    1.36
     itſelf
    1.28
     iſt
    1.23
     Diſ
    1.18
    ſelf
    1.18
     Monfieur
    1.16
     pleaſure
    1.16
     $_"
    1.13
     raiſ
    1.11
     juſt
    1.10
    Activations Density 0.918%

    No Known Activations